INDEX

Explanations

numerical values and measurements related to data or statistics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gregor

-0.60

 Greenberg

-0.59

top

-0.57

 Walters

-0.56

ner

-0.56

isi

-0.55

ant

-0.54

 لك

-0.54

ist

-0.53

es

-0.53

POSITIVE LOGITS

 للمعارف

1.25

ंदीखरीदारी

1.04

 Мексичка

0.97

 كومونز

0.93

 ujednoznacz

0.89

ɵɵ

0.89

 AssemblyCulture

0.88

########.

0.87

 الحره

0.86

 للاسماء

0.86

Activations Density 0.264%

numerical values and measurements related to data or statistics

No Comments

No Known Activations